pandas 3 设置值

from __future__ import print_function
import pandas as pd
import numpy as np

np.random.seed(1)
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=['A', 'B', 'C', 'D'])

赋值，新增列数据

df.iloc[2,2], df.loc['2013-01-03', 'D']

df.A[df.A>0], df['F']

df.iloc[2,2] = 1111                # 设置行列编号为2,2的数据只为1
df.loc['2013-01-03', 'D'] = 2222   # 设置行属性值为‘2013……’，列属性值为‘D’的值为2222
df[df.A>0] = 0    # 只保留列属性为‘A’且大于0的值，全部数据中的其他数据都设置为0
df.A[df.A>0] = 0  # 只更改列属性为‘A’的数据
df['F'] = np.nan  # 新增加一个属性列‘F’，所有的值为NaN
df['G']  = pd.Series([1,2,3,4,5,6], index=pd.date_range('20130101', periods=6)) # 新增一个列‘G’

以下是所有的运行结果：

print(df)

>                    A         B         C         D
> 2013-01-01  1.624345 -0.611756 -0.528172 -1.072969
> 2013-01-02  0.865408 -2.301539  1.744812 -0.761207
> 2013-01-03  0.319039 -0.249370  1.462108 -2.060141
> 2013-01-04 -0.322417 -0.384054  1.133769 -1.099891
> 2013-01-05 -0.172428 -0.877858  0.042214  0.582815
> 2013-01-06 -1.100619  1.144724  0.901591  0.502494

df.iloc[2,2] = 1111
print(df)

>                    A         B            C         D
> 2013-01-01  1.624345 -0.611756    -0.528172 -1.072969
> 2013-01-02  0.865408 -2.301539     1.744812 -0.761207
> 2013-01-03  0.319039 -0.249370  1111.000000 -2.060141
> 2013-01-04 -0.322417 -0.384054     1.133769 -1.099891
> 2013-01-05 -0.172428 -0.877858     0.042214  0.582815
> 2013-01-06 -1.100619  1.144724     0.901591  0.502494

df.loc['2013-01-03', 'D'] = 2222
print(df)

>                    A         B            C            D
> 2013-01-01  1.624345 -0.611756    -0.528172    -1.072969
> 2013-01-02  0.865408 -2.301539     1.744812    -0.761207
> 2013-01-03  0.319039 -0.249370  1111.000000  2222.000000
> 2013-01-04 -0.322417 -0.384054     1.133769    -1.099891
> 2013-01-05 -0.172428 -0.877858     0.042214     0.582815
> 2013-01-06 -1.100619  1.144724     0.901591     0.502494

df[df.A < 0] = 0
print(df)

>                    A         B         C         D
> 2013-01-01  1.624345 -0.611756 -0.528172 -1.072969
> 2013-01-02  0.865408 -2.301539  1.744812 -0.761207
> 2013-01-03  0.319039 -0.249370  1.462108 -2.060141
> 2013-01-04  0.000000  0.000000  0.000000  0.000000
> 2013-01-05  0.000000  0.000000  0.000000  0.000000
> 2013-01-06  0.000000  0.000000  0.000000  0.000000

df.A[df.A < 0] = 0
print(df)

>                    A         B         C         D
> 2013-01-01  1.624345 -0.611756 -0.528172 -1.072969
> 2013-01-02  0.865408 -2.301539  1.744812 -0.761207
> 2013-01-03  0.319039 -0.249370  1.462108 -2.060141
> 2013-01-04  0.000000 -0.384054  1.133769 -1.099891
> 2013-01-05  0.000000 -0.877858  0.042214  0.582815
> 2013-01-06  0.000000  1.144724  0.901591  0.502494

df['E'] = np.nan
print(df)

>                    A         B         C         D   E
> 2013-01-01  1.624345 -0.611756 -0.528172 -1.072969 NaN
> 2013-01-02  0.865408 -2.301539  1.744812 -0.761207 NaN
> 2013-01-03  0.319039 -0.249370  1.462108 -2.060141 NaN
> 2013-01-04  0.000000 -0.384054  1.133769 -1.099891 NaN
> 2013-01-05  0.000000 -0.877858  0.042214  0.582815 NaN
> 2013-01-06  0.000000  1.144724  0.901591  0.502494 NaN

df['G']  = pd.Series([1,2,3,4,5,6], index=pd.date_range('20130101', periods=6))
print(df)

>                    A         B         C         D   E  G
> 2013-01-01  1.624345 -0.611756 -0.528172 -1.072969 NaN  1
> 2013-01-02  0.865408 -2.301539  1.744812 -0.761207 NaN  2
> 2013-01-03  0.319039 -0.249370  1.462108 -2.060141 NaN  3
> 2013-01-04  0.000000 -0.384054  1.133769 -1.099891 NaN  4
> 2013-01-05  0.000000 -0.877858  0.042214  0.582815 NaN  5
> 2013-01-06  0.000000  1.144724  0.901591  0.502494 NaN  6

END